Merge tag 'for-linus-20180608' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes for this merge window, where some of them should go in
  sooner rather than later, hence a new pull this week. This pull
  request contains:

   - Set of NVMe fixes, mostly follow up cleanups/fixes to the queue
     changes, but also teardown/removal and misc changes (Christop/Dan/
     Johannes/Sagi/Steve).

   - Two lightnvm fixes for issues that showed up in this window
     (Colin/Wei).

   - Failfast/driver flags inheritance for flush requests (Hannes).

   - The md device put sanitization and fix (Kent).

   - dm bio_set inheritance fix (me).

   - nbd discard granularity fix (Josef).

   - nbd consistency in command printing (Kevin).

   - Loop recursion validation fix (Ted).

   - Partition overlap check (Wang)"

[ .. and now my build is warning-free again thanks to the md fix  - Linus ]

* tag 'for-linus-20180608' of git://git.kernel.dk/linux-block: (22 commits)
  nvme: cleanup double shift issue
  nvme-pci: make CMB SQ mod-param read-only
  nvme-pci: unquiesce dead controller queues
  nvme-pci: remove HMB teardown on reset
  nvme-pci: queue creation fixes
  nvme-pci: remove unnecessary completion doorbell check
  nvme-pci: remove unnecessary nested locking
  nvmet: filter newlines from user input
  nvme-rdma: correctly check for target keyed sgl support
  nvme: don't hold nvmf_transports_rwsem for more than transport lookups
  nvmet: return all zeroed buffer when we can't find an active namespace
  md: Unify mddev destruction paths
  dm: use bioset_init_from_src() to copy bio_set
  block: add bioset_init_from_src() helper
  block: always set partition number to '0' in blk_partition_remap()
  block: pass failfast and driver-specific flags to flush requests
  nbd: set discard_alignment to the granularity
  nbd: Consistently use request pointer in debug messages.
  block: add verifier for cmdline partition
  lightnvm: pblk: fix resource leak of invalid_bitmap
  ...

block/bio.c

@@ -1997,6 +1997,24 @@ int bioset_init(struct bio_set *bs,
 }
 EXPORT_SYMBOL(bioset_init);
 
+/*
+ * Initialize and setup a new bio_set, based on the settings from
+ * another bio_set.
+ */
+int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
+{
+	int flags;
+
+	flags = 0;
+	if (src->bvec_pool.min_nr)
+		flags |= BIOSET_NEED_BVECS;
+	if (src->rescue_workqueue)
+		flags |= BIOSET_NEED_RESCUER;
+
+	return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags);
+}
+EXPORT_SYMBOL(bioset_init_from_src);
+
 #ifdef CONFIG_BLK_CGROUP
 
 /**

block/blk-core.c

@@ -2220,10 +2220,10 @@ static inline int blk_partition_remap(struct bio *bio)
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
-		bio->bi_partno = 0;
 		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
 				      bio->bi_iter.bi_sector - p->start_sect);
 	}
+	bio->bi_partno = 0;
 	ret = 0;
 out:
 	rcu_read_unlock();

block/blk-flush.c

@@ -94,7 +94,7 @@ enum {
 };
 
 static bool blk_kick_flush(struct request_queue *q,
-			   struct blk_flush_queue *fq);
+			   struct blk_flush_queue *fq, unsigned int flags);
 
 static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 {
@@ -212,7 +212,7 @@ static bool blk_flush_complete_seq(struct request *rq,
 		BUG();
 	}
 
-	kicked = blk_kick_flush(q, fq);
+	kicked = blk_kick_flush(q, fq, rq->cmd_flags);
 	return kicked | queued;
 }
 
@@ -281,6 +281,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
  * @fq: flush queue
+ * @flags: cmd_flags of the original request
  *
  * Flush related states of @q have changed, consider issuing flush request.
  * Please read the comment at the top of this file for more info.
@@ -291,7 +292,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
  * RETURNS:
  * %true if flush was issued, %false otherwise.
  */
-static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
+static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
+			   unsigned int flags)
 {
 	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	struct request *first_rq =
@@ -346,6 +348,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
+	flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK);
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;

block/partitions/cmdline.c

@@ -58,6 +58,62 @@ static int __init cmdline_parts_setup(char *s)
 }
 __setup("blkdevparts=", cmdline_parts_setup);
 
+static bool has_overlaps(sector_t from, sector_t size,
+			 sector_t from2, sector_t size2)
+{
+	sector_t end = from + size;
+	sector_t end2 = from2 + size2;
+
+	if (from >= from2 && from < end2)
+		return true;
+
+	if (end > from2 && end <= end2)
+		return true;
+
+	if (from2 >= from && from2 < end)
+		return true;
+
+	if (end2 > from && end2 <= end)
+		return true;
+
+	return false;
+}
+
+static inline void overlaps_warns_header(void)
+{
+	pr_warn("Overlapping partitions are used in command line partitions.");
+	pr_warn("Don't use filesystems on overlapping partitions:");
+}
+
+static void cmdline_parts_verifier(int slot, struct parsed_partitions *state)
+{
+	int i;
+	bool header = true;
+
+	for (; slot < state->limit && state->parts[slot].has_info; slot++) {
+		for (i = slot+1; i < state->limit && state->parts[i].has_info;
+		     i++) {
+			if (has_overlaps(state->parts[slot].from,
+					 state->parts[slot].size,
+					 state->parts[i].from,
+					 state->parts[i].size)) {
+				if (header) {
+					header = false;
+					overlaps_warns_header();
+				}
+				pr_warn("%s[%llu,%llu] overlaps with "
+					"%s[%llu,%llu].",
+					state->parts[slot].info.volname,
+					(u64)state->parts[slot].from << 9,
+					(u64)state->parts[slot].size << 9,
+					state->parts[i].info.volname,
+					(u64)state->parts[i].from << 9,
+					(u64)state->parts[i].size << 9);
+			}
+		}
+	}
+}
+
 /*
  * Purpose: allocate cmdline partitions.
  * Returns:
@@ -93,6 +149,7 @@ int cmdline_partition(struct parsed_partitions *state)
 	disk_size = get_capacity(state->bdev->bd_disk) << 9;
 
 	cmdline_parts_set(parts, disk_size, 1, add_part, (void *)state);
+	cmdline_parts_verifier(1, state);
 
 	strlcat(state->pp_buf, "\n", PAGE_SIZE);
 

drivers/block/loop.c

@@ -647,6 +647,36 @@ static void loop_reread_partitions(struct loop_device *lo,
 			__func__, lo->lo_number, lo->lo_file_name, rc);
 }
 
+static inline int is_loop_device(struct file *file)
+{
+	struct inode *i = file->f_mapping->host;
+
+	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
+}
+
+static int loop_validate_file(struct file *file, struct block_device *bdev)
+{
+	struct inode	*inode = file->f_mapping->host;
+	struct file	*f = file;
+
+	/* Avoid recursion */
+	while (is_loop_device(f)) {
+		struct loop_device *l;
+
+		if (f->f_mapping->host->i_bdev == bdev)
+			return -EBADF;
+
+		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
+		if (l->lo_state == Lo_unbound) {
+			return -EINVAL;
+		}
+		f = l->lo_backing_file;
+	}
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -676,14 +706,15 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!file)
 		goto out;
 
+	error = loop_validate_file(file, bdev);
+	if (error)
+		goto out_putf;
+
 	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
 
-	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
-		goto out_putf;
-
 	/* size of the new backing store needs to be the same */
 	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
 		goto out_putf;
@@ -709,13 +740,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	return error;
 }
 
-static inline int is_loop_device(struct file *file)
-{
-	struct inode *i = file->f_mapping->host;
-
-	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
-}
-
 /* loop sysfs attributes */
 
 static ssize_t loop_attr_show(struct device *dev, char *page,
@@ -881,7 +905,7 @@ static int loop_prepare_queue(struct loop_device *lo)
 static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		       struct block_device *bdev, unsigned int arg)
 {
-	struct file	*file, *f;
+	struct file	*file;
 	struct inode	*inode;
 	struct address_space *mapping;
 	int		lo_flags = 0;
@@ -900,29 +924,13 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (lo->lo_state != Lo_unbound)
 		goto out_putf;
 
-	/* Avoid recursion */
-	f = file;
-	while (is_loop_device(f)) {
-		struct loop_device *l;
-
-		if (f->f_mapping->host->i_bdev == bdev)
-			goto out_putf;
-
-		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
-		if (l->lo_state == Lo_unbound) {
-			error = -EINVAL;
-			goto out_putf;
-		}
-		f = l->lo_backing_file;
-	}
+	error = loop_validate_file(file, bdev);
+	if (error)
+		goto out_putf;
 
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
-	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
-		goto out_putf;
-
 	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
 	    !file->f_op->write_iter)
 		lo_flags |= LO_FLAGS_READ_ONLY;

drivers/block/nbd.c

@@ -246,6 +246,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 
 	if (config->flags & NBD_FLAG_SEND_TRIM) {
 		nbd->disk->queue->limits.discard_granularity = config->blksize;
+		nbd->disk->queue->limits.discard_alignment = config->blksize;
 		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
 	}
 	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
@@ -275,7 +276,7 @@ static void nbd_complete_rq(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
-	dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd,
+	dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", req,
 		cmd->status ? "failed" : "done");
 
 	blk_mq_end_request(req, cmd->status);
@@ -482,7 +483,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	memcpy(request.handle, &tag, sizeof(tag));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
-		cmd, nbdcmd_to_ascii(type),
+		req, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, index, 1, &from,
 			(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
@@ -518,7 +519,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 			int flags = is_last ? 0 : MSG_MORE;
 
 			dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n",
-				cmd, bvec.bv_len);
+				req, bvec.bv_len);
 			iov_iter_bvec(&from, ITER_BVEC | WRITE,
 				      &bvec, 1, bvec.bv_len);
 			if (skip) {
@@ -610,7 +611,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return cmd;
 	}
 
-	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", cmd);
+	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
 	if (rq_data_dir(req) != WRITE) {
 		struct req_iterator iter;
 		struct bio_vec bvec;
@@ -637,7 +638,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 				return ERR_PTR(-EIO);
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
-				cmd, bvec.bv_len);
+				req, bvec.bv_len);
 		}
 	} else {
 		/* See the comment in nbd_queue_rq. */
@@ -1062,6 +1063,7 @@ static void nbd_config_put(struct nbd_device *nbd)
 
 		nbd->tag_set.timeout = 0;
 		nbd->disk->queue->limits.discard_granularity = 0;
+		nbd->disk->queue->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 
@@ -1516,6 +1518,7 @@ static int nbd_dev_add(int index)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	disk->queue->limits.discard_granularity = 0;
+	disk->queue->limits.discard_alignment = 0;
 	blk_queue_max_discard_sectors(disk->queue, 0);
 	blk_queue_max_segment_size(disk->queue, UINT_MAX);
 	blk_queue_max_segments(disk->queue, USHRT_MAX);

drivers/lightnvm/pblk-gc.c

@@ -203,7 +203,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 		if (!lba_list) {
 			pr_err("pblk: could not interpret emeta (line %d)\n",
 					line->id);
-			goto fail_free_ws;
+			goto fail_free_invalid_bitmap;
 		}
 	}
 
@@ -280,6 +280,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	kfree(gc_rq);
 fail_free_lba_list:
 	pblk_mfree(lba_list, l_mg->emeta_alloc_type);
+fail_free_invalid_bitmap:
 	kfree(invalid_bitmap);
 fail_free_ws:
 	kfree(line_ws);

drivers/lightnvm/pblk-init.c

@@ -20,7 +20,7 @@
 
 #include "pblk.h"
 
-unsigned int write_buffer_size;
+static unsigned int write_buffer_size;
 
 module_param(write_buffer_size, uint, 0644);
 MODULE_PARM_DESC(write_buffer_size, "number of entries in a write buffer");